Research - Papers
Explore a selection of our published work on a variety of key research challenges in AI.
Challenges in Algorithmic Debiasing for Toxic Language Detection
Biased associations have been a challenge in the development of classifiers for detecting toxic language, hindering both fairness and accuracy. As potential solutions, we investigate recently…
Challenges in Automated Debiasing for Toxic Language Detection
Biased associations have been a challenge in the development of classifiers for detecting toxic language, hindering both fairness and accuracy. As potential solutions, we investigate recently…
Discourse Understanding and Factual Consistency in Abstractive Summarization
We introduce Cooperative Generator-Discriminator Networks (Co-opNet), a general framework for abstractive summarization with distinct modeling of the narrative flow in the output summary. Most…
Evaluating the Evaluation of Diversity in Natural Language Generation
Despite growing interest in natural language generation (NLG) models that produce diverse outputs, there is currently no principled method for evaluating the diversity of an NLG system. In this…
First Align, then Predict: Understanding the Cross-Lingual Ability of Multilingual BERT
Multilingual pretrained language models have demonstrated remarkable zero-shot crosslingual transfer capabilities. Such transfer emerges by fine-tuning on a task of interest in one language and…
CLIPScore: A Reference-free Evaluation Metric for Image Captioning
Image captioning has conventionally relied on reference-based automatic evaluations, where machine captions are compared against captions written by humans. This is in contrast to the reference-free…
Misinfo Reaction Frames: Reasoning about Readers' Reactions to News Headlines (preprint)
Even to a simple and short news headline, readers react in a multitude of ways: cognitively (e.g., inferring the writer's intent), emotionally (e.g., feeling distrust), and behaviorally (e.g.,…
Contrasting Contrastive Self-Supervised Representation Learning Pipelines
In the past few years, we have witnessed remarkable breakthroughs in self-supervised representation learning. Despite the success and adoption of representations learned through this paradigm, much…
GridToPix: Training Embodied Agents with Minimal Supervision
While deep reinforcement learning (RL) promises freedom from hand-labeled data, great successes, especially for Embodied AI, require significant work to create supervision via carefully shaped…
“I’m Not Mad”: Commonsense Implications of Negation and Contradiction
Natural language inference requires reasoning about contradictions, negations, and their commonsense implications. Given a simple premise (e.g., “I’m mad at you”), humans can reason about the…